A smart factory application method and system based on real-time database

Abstract

The present invention is applicable to the field of intelligent factory cutting processing technology, and provides an intelligent factory application method and system based on a real-time database, the method comprising: obtaining the initial cutting speed of the target tool for the target workpiece, and extracting the historical processing log of the target tool in the intelligent factory, and at the same time identifying the surface coating type of the target workpiece in real time through visual detection technology, and obtaining the current surface coating roughness value; parsing the historical processing log, screening out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, and extracting the load data of the target tool under different coating thickness conditions from the screened historical workpiece processing records. The present invention effectively integrates macro trends and local characteristics to form a global and local collaborative processing optimization mechanism. By comprehensively correcting the cutting speed, the tool load adaptability is significantly improved, the tool life is extended, and the stability and surface quality of workpiece processing are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent factory cutting processing, and in particular relates to an intelligent factory application method and system based on a real-time database. Background Art

[0002] In the existing intelligent factory processing system, cutting processing, as an important process for high-precision manufacturing, is widely used in the efficient production of complex workpieces. Existing technologies usually rely on preset cutting process parameter libraries, such as the initial cutting speed and processing conditions recommended by tool manufacturers. These parameters are designed based on the general characteristics of the workpiece material and can meet the needs of most common working conditions. However, for complex workpieces with special coatings on the surface, the existing technology has significant deficiencies in cutting parameter optimization. For example, changes in coating thickness may lead to increased tool load, and differences in coating roughness will affect cutting stability. Traditional static parameter settings are difficult to adapt to such complex working conditions.

[0003] With the development of industrial technology, some systems have introduced historical processing data and real-time detection technology to improve the processing process. For example, the performance of the tool under different working conditions is recorded in the historical processing log to provide data support for parameter optimization; the surface coating characteristics of the workpiece are identified in real time through visual inspection technology to enhance the perception of coating differences. However, the integrated application of these technologies is still limited. Existing systems often only adjust a single parameter, lacking an optimization mechanism that combines macro trends and local characteristics, resulting in insufficient accuracy in cutting parameter adjustment. This lack of accuracy often causes the actual processing speed of the tool to not match the processing requirements of the workpiece. It may be too high, resulting in increased load and increased wear, or too low to reduce processing efficiency, further accelerating the aging of the tool and affecting its service life and processing stability. Summary of the invention

[0004] The purpose of the present invention is to provide a smart factory application method and system based on a real-time database, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: a smart factory application method based on a real-time database, the method comprising:

[0006] Obtain the initial cutting speed of the target tool for the target workpiece, extract the historical processing log of the target tool in the smart factory, and use visual inspection technology to identify the type of surface coating of the target workpiece in real time and obtain the current surface coating roughness value;

[0007] Analyze the historical processing logs, select the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extract the load data of the target tool under different coating thickness conditions from the selected historical workpiece processing records, and generate a load characteristic curve in order of coating thickness from small to large;

[0008] Analyze the load characteristic curve to determine whether it shows a positive trend. If so, determine that the type of surface coating has a deterioration characteristic on the load of the target tool, and extract the average slope value of the load characteristic curve as the first correction factor;

[0009] Analyze the load characteristic curve, identify the load abnormal points, locate the surface coating roughness values ​​of the historical workpieces corresponding to these load abnormal points through the historical processing logs, perform statistical analysis on these surface coating roughness values, generate standardized reference surface coating roughness values, and calculate the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor;

[0010] The initial cutting speed is comprehensively corrected by combining the first correction factor and the second correction factor, and the optimized cutting speed is calculated.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the steps of parsing the historical processing log, screening out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extracting the load data of the target tool under different coating thickness conditions from the screened historical workpiece processing records, and generating a load characteristic curve in order of coating thickness from small to large include:

[0012] Analyze the historical processing logs of the smart factory and select the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type;

[0013] Extract the load data of the target tool under different coating thicknesses from the selected historical workpiece processing records, where the load data is the ratio of the spindle power to the rated power of the machine where the target tool is located, and organize it into a matching data table corresponding to the coating thickness and load data;

[0014] Based on the matching data table, a load characteristic curve is generated with coating thickness as the horizontal axis and load data as the vertical axis.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, the steps of analyzing the load characteristic curve to determine whether it presents a positive trend, and if so, determining that the type of surface coating has a degradation characteristic on the load of the target tool, and extracting the average slope value of the load characteristic curve as the first correction factor include:

[0016] Analyze the overall trend of the load characteristic curve to determine whether the load data shows an overall upward relationship with the increase of coating thickness;

[0017] If it is determined that the load data as a whole increases with the coating thickness, it is determined that the type of surface coating has a deteriorating characteristic for the load of the target tool;

[0018] Based on the load characteristic curve, an average slope value is extracted and used as the first correction factor.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the steps of parsing the load characteristic curve, identifying load abnormal points, locating the surface coating roughness values ​​of historical workpieces corresponding to these load abnormal points through historical processing logs, and performing statistical analysis on these surface coating roughness values ​​to generate standardized reference surface coating roughness values, and calculating the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor include:

[0020] Analyze the load characteristic curve and screen out abnormal load points, where the load data does not increase as the coating thickness increases according to the overall trend of the load characteristic curve, but decreases or remains unchanged;

[0021] Through the historical processing logs of the smart factory, the historical workpiece processing records corresponding to these load anomalies are located, the surface coating roughness values ​​of these historical workpieces are extracted, and statistical analysis is performed on them. The average value is calculated or the median value is selected after denoising to generate a standardized reference surface coating roughness value;

[0022] The current surface coating roughness value of the target workpiece is compared with the reference surface coating roughness value, and the deviation between the two is quantified and used as the second correction factor.

[0023] As a further limitation of the technical solution of the embodiment of the present invention, the steps of comprehensively correcting the initial cutting speed by combining the first correction factor and the second correction factor to calculate the optimized cutting speed include:

[0024] The cutting speed optimization formula is retrieved, and the initial cutting speed is comprehensively corrected by combining the first correction factor and the second correction factor, and the optimized cutting speed is calculated;

[0025] The optimized cutting speed is applied to the cutting process of the target tool.

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the cutting speed optimization formula is: , where N opt Refers to the optimized cutting speed, N initrefers to the initial cutting speed, F1 refers to the first correction factor, that is, the average slope value of the load characteristic curve, K1 is the adjustment coefficient for adjusting the first correction factor, F2 is the second correction factor, that is, the deviation between the current surface coating roughness value and the reference surface coating roughness value, K2 is the adjustment coefficient for adjusting the second correction factor, and the value range of K1 and K2 is 0.1 to 0.5;

[0027] In the cutting speed optimization formula, , where R current Refers to the current surface coating roughness value, R ref Refers to the reference surface coating roughness value.

[0028] A smart factory application system based on a real-time database, the system comprising: a data acquisition module, a load characteristic curve drawing module, a first correction factor determination module, a second correction factor determination module and a cutting speed optimization module, wherein:

[0029] The data acquisition module is used to obtain the initial cutting speed of the target tool for the target workpiece, and extract the historical processing log of the target tool in the smart factory. At the same time, it uses visual inspection technology to identify the type of surface coating of the target workpiece in real time and obtain the current surface coating roughness value;

[0030] A load characteristic curve drawing module is used to parse historical processing logs, screen out historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extract the load data of the target tool under different coating thickness conditions from the screened historical workpiece processing records, and generate a load characteristic curve in order of coating thickness from small to large;

[0031] A first correction factor determination module is used to analyze the load characteristic curve to determine whether it shows a positive trend. If so, it is determined that the type of surface coating has a degradation characteristic on the load of the target tool, and the average slope value of the load characteristic curve is extracted as the first correction factor;

[0032] The second correction factor determination module is used to analyze the load characteristic curve, identify the load abnormal points, locate the surface coating roughness values ​​of the historical workpieces corresponding to these load abnormal points through the historical processing logs, and perform statistical analysis on these surface coating roughness values ​​to generate standardized reference surface coating roughness values, and calculate the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor;

[0033] The cutting speed optimization module is used to combine the first correction factor and the second correction factor to comprehensively correct the initial cutting speed and calculate the optimized cutting speed.

[0034] As a further limitation of the technical solution of the embodiment of the present invention, the load characteristic curve drawing module specifically includes:

[0035] The log screening unit is used to parse the historical processing logs of the smart factory and screen out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type;

[0036] A matching data table arrangement unit is used to extract the load data of the target tool under different coating thicknesses from the screened historical workpiece processing records, wherein the load data is the ratio of the spindle power to the rated power of the machine where the target tool is located, and arrange it into a matching data table corresponding to the coating thickness and the load data;

[0037] The load characteristic curve generating unit is used to generate a load characteristic curve based on the matching data table, with the coating thickness as the horizontal axis and the load data as the vertical axis.

[0038] As a further limitation of the technical solution of the embodiment of the present invention, the first correction factor determination module specifically includes:

[0039] The trend analysis unit is used to analyze the overall trend of the load characteristic curve to determine whether the load data shows an overall upward relationship with the increase of coating thickness;

[0040] A degradation characteristic determination unit, for determining that the surface coating type has a degradation characteristic for the load of the target tool when it is determined that the load data as a whole increases with the coating thickness;

[0041] The average slope value calculation unit is used to extract the average slope value based on the load characteristic curve and use it as the first correction factor.

[0042] As a further limitation of the technical solution of the embodiment of the present invention, the second correction factor determination module specifically includes:

[0043] A load abnormal point determination unit is used to analyze the load characteristic curve and screen out load abnormal points, wherein the load abnormal point refers to a point where the load data does not increase as the coating thickness increases according to the overall trend of the load characteristic curve, but decreases or remains unchanged;

[0044] A reference roughness value generating unit is used to locate the historical workpiece processing records corresponding to these load abnormal points through the historical processing logs of the smart factory, extract the surface coating roughness values ​​of these historical workpieces, and perform statistical analysis on them, and generate a standardized reference surface coating roughness value by calculating the average value or selecting the median value after denoising;

[0045] The deviation quantification unit is used to compare the current surface coating roughness value of the target workpiece with the reference surface coating roughness value, quantify the deviation between the two, and use it as the second correction factor.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention combines historical processing logs with real-time detection data to accurately optimize cutting parameters. Based on the trend data extracted from the load characteristic curve, it quantifies the effect of the target workpiece surface coating thickness on the tool load; at the same time, by real-time detection of the target workpiece surface coating roughness, it compares it with the standardized reference value to generate a dynamic correction factor. This method can not only adjust the initial cutting speed to adapt to load changes, but also perform refined optimization for the local characteristics of the coating.

[0048] Compared with the existing technology, the present invention effectively integrates macro trends and local characteristics to form a global and local collaborative processing optimization mechanism. By comprehensively correcting the cutting speed, the tool load adaptability is significantly improved, the tool life is extended, and the stability and surface quality of workpiece processing are improved. This method is particularly suitable for efficient processing scenarios of complex coated workpieces. It has both adaptability and precision, and meets the dual requirements of smart factories for processing accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0050] Figure 2 A flow chart of drawing a load characteristic curve based on a historical processing log in a method provided by an embodiment of the present invention;

[0051] Figure 3 A flow chart of generating a first correction factor based on a load characteristic curve in a method provided in an embodiment of the present invention;

[0052] Figure 4 A flow chart of generating a second correction factor based on a current surface coating roughness value and a reference surface coating roughness value in a method provided by an embodiment of the present invention;

[0053] Figure 5 A flowchart of a smart factory application method based on a real-time database in a method provided by an embodiment of the present invention;

[0054] Figure 6 An application architecture diagram of a system provided by an embodiment of the present invention;

[0055] Figure 7 A structural block diagram of a load characteristic curve drawing module in a system provided by an embodiment of the present invention;

[0056] Figure 8 A structural block diagram of a first correction factor determination module in a system provided by an embodiment of the present invention;

[0057] Fig. 9 This is a structural block diagram of a second correction factor determination module in a system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0060] Specifically, a smart factory application method based on a real-time database comprises the following steps:

[0061] Step S100, obtaining the initial cutting speed of the target tool for the target workpiece, and extracting the historical processing log of the target tool in the smart factory, while using visual inspection technology to identify the type of surface coating of the target workpiece in real time and obtain the current surface coating roughness value.

[0062] In the embodiment of the present invention, in the smart factory to which the present invention is applied, cutting processing is an important application scenario, and efficient and precise processing of the target workpiece is achieved through intelligent processing procedures. The smart factory integrates real-time databases, online monitoring equipment and visual inspection technology, can dynamically respond to processing requirements and optimize processing parameters, and provides a highly intelligent solution for the processing of special workpieces.

[0063] The initial cutting speed usually comes from a preset cutting process parameter library. This parameter library is based on the recommended values ​​provided by the tool manufacturer, combined with the basic properties of the workpiece material (such as hardness, strength) and the cutting environment (such as coolant usage conditions). However, in the prior art, the setting of the initial cutting speed rarely fully considers the impact of special coatings on the surface of the target workpiece. Special coatings may cause increased cutting forces, increased tool wear, and other phenomena, and this complexity is often ignored in traditional processes. Therefore, using only preset parameters may not be able to effectively meet the processing needs of target workpieces with special coatings.

[0064] The historical processing logs of the target tool are automatically recorded and stored in the real-time database of the smart factory. These logs include the cutting records of the target tool under different workpieces and different process parameters, such as cutting speed, cutting depth, coating thickness, spindle power, tool wear status and other key data. These data usually come from online monitoring equipment during the operation of the tool, such as spindle power sensors, cutting force sensors, and workpiece surface detection systems. Through the integrated analysis of these data, a performance model of the tool under specific processing conditions can be generated, providing a reference for the subsequent processing optimization of similar workpieces.

[0065] Real-time identification of the type of surface coating and the current coating roughness value of the target workpiece through visual inspection technology requires the help of high-precision industrial cameras and data processing algorithms. The industrial camera captures the surface of the target workpiece and collects image data; combined with multispectral imaging technology, the reflectivity and absorptivity characteristics of different coating materials within the spectral range are used to identify the type of coating. At the same time, the detection of coating roughness can be achieved through laser interferometry technology or optical profilometers. These devices can measure the microscopic characteristics of the surface with high precision and convert the results into roughness values. The detection process is linked to the real-time database to store the collected coating types and roughness data in real time, which is convenient for the adjustment of subsequent processing parameters. Through this intelligent detection process, it is possible to dynamically adapt to changes in the coating characteristics of the target workpiece and improve the accuracy and efficiency of processing.

[0066] Furthermore, the smart factory application method based on real-time database also includes the following steps:

[0067] Step S200, parse the historical processing log, filter out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extract the load data of the target tool under different coating thickness conditions from the filtered historical workpiece processing records, and generate a load characteristic curve in order of coating thickness from small to large.

[0068] Specifically, Figure 2 A flow chart for drawing a load characteristic curve based on historical processing logs is shown.

[0069] The process of parsing the historical processing logs, screening out the historical processing records of workpieces that are consistent with the target workpiece type and have the same surface coating type, extracting the load data of the target tool under different coating thickness conditions from the screened historical processing records, and generating the load characteristic curve in order of coating thickness from small to large specifically includes the following steps:

[0070] Step S201, parsing the historical processing logs of the smart factory, and screening out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type;

[0071] Step S202, extracting load data of a target tool under different coating thicknesses from the screened historical workpiece processing records, wherein the load data is a ratio of a spindle power to a rated power of a machine where the target tool is located, and arranging the data into a matching data table corresponding to coating thickness and load data;

[0072] Step S203 , based on the matching data table, a load characteristic curve is generated with the coating thickness as the horizontal axis and the load data as the vertical axis.

[0073] In an embodiment of the present invention, the load data of the target tool under different coating thicknesses is extracted from the screened historical workpiece processing records, and the real-time database and online monitoring technology of the smart factory are relied on for implementation. First, the spindle power data and rated power value during the processing are extracted from the screened records through the historical processing log parsing technology, and the spindle power and rated power are calculated as the ratio of the spindle power to the rated power. This ratio can be completed by the automatic calculation module of the database and stored in the corresponding load data field. At the same time, the corresponding coating thickness information in each record is matched, and a matching table of coating thickness and load data is generated to ensure that the data is clear and complete.

[0074] The ratio of the spindle power to the rated power of the machine where the target tool is located is selected as the measurement indicator of load data, mainly because this ratio can intuitively reflect the changing characteristics of the tool cutting load. The spindle power is directly affected by the cutting force, and the rated power provides a benchmark value for mechanical performance. The actual load level of the machine can be quantified through the ratio of the two. At the same time, this ratio is dimensionless, which is convenient for data comparison and analysis under different working conditions. Although other types of load data can be selected, such as three-axis cutting force, vibration amplitude, etc., the acquisition of these data usually requires additional high-precision sensors, which is more complicated, while the spindle power ratio can be directly collected and calculated through existing equipment, which has higher practicality and consistency.

[0075] Based on the matching data table, with coating thickness as the horizontal axis and load data as the vertical axis, the significance of generating a load characteristic curve is to provide a global view of the relationship between coating thickness and tool load. This curve can intuitively show the trend of load changes with coating thickness, and provides a data basis for analyzing the impact of the target workpiece surface coating on the tool load. The generation of the load characteristic curve is based on linear or nonlinear fitting methods, which can extract regularities from discrete matching data and eliminate the interference of abnormal data. Through this curve, load abnormal points can be identified, load deterioration trends can be evaluated, and a scientific basis can be further provided for the correction of cutting parameters.

[0076] Furthermore, the smart factory application method based on real-time database also includes the following steps:

[0077] Step S300, analyzing the load characteristic curve to determine whether it presents a positive trend. If so, determining that the type of surface coating has a degradation characteristic in affecting the load of the target tool, and extracting the average slope value of the load characteristic curve as the first correction factor.

[0078] Specifically, Figure 3 A flow chart for generating a first correction factor based on a load characteristic curve is shown.

[0079] The load characteristic curve is analyzed to determine whether it shows a positive trend. If so, it is determined that the type of surface coating has a degradation characteristic on the load of the target tool, and the average slope value of the load characteristic curve is extracted as the first correction factor, which specifically includes the following steps:

[0080] Step S301, analyzing the overall trend of the load characteristic curve to determine whether the load data shows an overall obvious upward relationship with the increase of coating thickness;

[0081] Step S302, if it is determined that the load data as a whole increases with the coating thickness, it is determined that the surface coating type has a deterioration characteristic on the load of the target tool;

[0082] Step S303: extract the average slope value based on the load characteristic curve and use it as the first correction factor. The method of extracting the average slope value based on the load characteristic curve belongs to the prior art and is usually implemented by data analysis methods such as linear regression or polynomial fitting. It is widely used to describe parameter change trends and quantify their impact.

[0083] In an embodiment of the present invention, the overall trend of the load characteristic curve is analyzed, and it is necessary to combine data fitting technology and statistical analysis methods for specific implementation. First, the load characteristic curve is trend analyzed by linear regression or polynomial fitting technology, and the overall relationship between the load data and the coating thickness is expressed by a mathematical model. Linear regression can provide a clear trend direction, while polynomial fitting is suitable for more complex nonlinear changes. By calculating the slope of the trend line, it can be determined whether the load data shows an overall upward relationship with the increase in coating thickness. If the slope is positive and the fitting result shows that the overall trend increases significantly, it is determined that the load has a positive relationship. This analysis applies existing statistical methods and curve fitting algorithms, and is usually completed by data analysis software or the factory's real-time database analysis module.

[0084] "Determining that the type of surface coating has degradation characteristics for the target tool load" is of great significance. Through this judgment, the degree and direction of the impact of the target workpiece surface coating on the tool load can be clarified. If it is determined to be a degradation characteristic, it means that the coating may increase the tool load, aggravate tool wear, and reduce processing efficiency. This conclusion not only provides a basis for the optimization of processing parameters, but also helps factories evaluate the processing feasibility of workpieces with different coatings, and even provides feedback for tool design and processing technology improvements. After clarifying the degradation characteristics, targeted adjustments can be made before processing to avoid tool failure or processing failure due to improper parameter settings.

[0085] The significance of adjusting the initial cutting speed by extracting the average slope value based on the load characteristic curve and using it as the first correction factor is to achieve dynamic optimization of processing parameters. The average slope value reflects the overall growth rate of the load as the coating thickness increases, and is the core indicator for quantifying the degree of load degradation. By introducing this correction factor, the cutting speed can be optimized in a targeted manner based on historical data and coating characteristics to ensure that the processing parameters match the characteristics of the target workpiece. The advantage of such an adjustment is that it can reduce the instantaneous load peak of the tool, extend the tool life, and improve processing stability and surface quality. Compared with the traditional static parameter setting method, this dynamic adjustment is based on actual data trends, can better adapt to changes in complex workpieces and processing conditions, and improve the processing efficiency and precision of smart factories.

[0086] Furthermore, the smart factory application method based on real-time database also includes the following steps:

[0087] Step S400, analyze the load characteristic curve, identify load abnormal points, locate the surface coating roughness values ​​of historical workpieces corresponding to these load abnormal points through historical processing logs, perform statistical analysis on these surface coating roughness values, generate standardized reference surface coating roughness values, and calculate the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor.

[0088] Specifically, Figure 4 A flow chart for generating a second correction factor based on a current surface coating roughness value and a reference surface coating roughness value is shown.

[0089] Among them, parsing the load characteristic curve, identifying the load abnormal points, locating the surface coating roughness values ​​of the historical workpieces corresponding to these load abnormal points through the historical processing logs, and performing statistical analysis on these surface coating roughness values ​​to generate standardized reference surface coating roughness values, and calculating the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor, specifically including the following steps:

[0090] Step S401, analyzing the load characteristic curve to screen out abnormal load points, wherein the abnormal load points refer to the load data of the load points not increasing as the coating thickness increases according to the overall trend of the load characteristic curve, but decreasing or remaining unchanged;

[0091] Step S402, locating the historical workpiece processing records corresponding to these load abnormal points through the historical processing logs of the smart factory, extracting the surface coating roughness values ​​of these historical workpieces, and performing statistical analysis on them, using a method of calculating the average value or selecting the median after denoising to generate a standardized reference surface coating roughness value;

[0092] Step S403: Compare the current surface coating roughness value of the target workpiece with the reference surface coating roughness value, quantify the deviation between the two, and use it as a second correction factor.

[0093] In the embodiment of the present invention, the significance of screening outlier load points is to identify outlier data that does not conform to the overall trend by analyzing the load characteristic curve, thereby revealing the potential impact of coating characteristics on tool load. Outliers are usually manifested as load data that decreases, remains unchanged, or increases significantly below the normal trend as the coating thickness increases. These outliers may be closely related to the local characteristics of the coating on the workpiece surface, especially when the coating roughness is too low, uneven, or there are local anomalies. By screening these data points, the specific impact of surface coating roughness on load changes can be further analyzed, and key factors that have a significant impact on tool performance and processing stability can be found, thereby providing a more targeted reference for processing parameter optimization.

[0094] Through the historical processing logs of the smart factory, the historical workpiece processing records corresponding to the load abnormal points are located, which requires real-time database and data analysis technology. The specific implementation process includes the following steps: First, extract the abnormal point data marked in the load characteristic curve and obtain the workpiece identification code associated with these points; then, through the historical processing log query interface of the smart factory, locate the coating thickness, cutting parameters and coating roughness values ​​of these workpieces during the processing process; then, perform statistical analysis on the extracted surface coating roughness values, and use the denoising technology in signal processing (such as filtering or threshold removal) to remove abnormal data points to ensure the reliability and representativeness of the data; finally, calculate the average value of the roughness value or select the median value to generate a standardized reference surface coating roughness value. In this process, existing technologies such as database query, statistical analysis and signal processing are used to ensure that the generated reference value can truly reflect the coating characteristics of the load abnormal points.

[0095] Comparing the current surface coating roughness value of the target workpiece with the reference surface coating roughness value, quantifying the deviation between the two, and using this as the second correction factor is of great significance and obvious benefits. Through the quantification of the deviation, the processing parameters can be dynamically adjusted to better adapt to the actual characteristics of the current workpiece surface, avoiding cutting instability, tool overload or workpiece quality problems caused by roughness deviation. At the same time, this adjustment method can effectively reduce tool wear, extend tool life, and improve the quality of the machined surface. The advantage of using the second correction factor to optimize the processing process is that it can accurately adjust the parameters at the microscopic characteristic level, which is especially suitable for high-precision processing requirements. Compared with a single correction factor, this dual-factor adjustment mechanism further enhances the adaptability and intelligence level of processing, and improves the robustness and efficiency of the overall process.

[0096] Furthermore, the smart factory application method based on real-time database also includes the following steps:

[0097] Step S500, combining the first correction factor and the second correction factor, comprehensively correcting the initial cutting speed, and calculating the optimized cutting speed.

[0098] Specifically, Figure 5 A flow chart of a smart factory application method based on a real-time database is shown.

[0099] The initial cutting speed is comprehensively corrected by combining the first correction factor and the second correction factor, and the optimized cutting speed is calculated, which specifically includes the following steps:

[0100] Step S501, calling the cutting speed optimization formula, and combining the first correction factor and the second correction factor to perform comprehensive correction on the initial cutting speed, and calculate the optimized cutting speed;

[0101] Step S502, applying the optimized cutting speed to the cutting process of the target tool.

[0102] The cutting speed optimization formula is: , where N opt Refers to the optimized cutting speed, N init refers to the initial cutting speed, F1 refers to the first correction factor, that is, the average slope value of the load characteristic curve, K1 is the adjustment coefficient for adjusting the first correction factor, F2 is the second correction factor, that is, the deviation between the current surface coating roughness value and the reference surface coating roughness value, K2 is the adjustment coefficient for adjusting the second correction factor, and the value range of K1 and K2 is 0.1 to 0.5;

[0103] In the cutting speed optimization formula, , where R currentRefers to the current surface coating roughness value, R ref Refers to the reference surface coating roughness value.

[0104] In the embodiment of the present invention, the significance of the linkage between the first correction factor and the second correction factor is to combine the load characteristic trend with the local characteristics of the coating surface to build a more comprehensive processing parameter optimization model. The first correction factor quantifies the overall trend of the load changing with the coating thickness based on the average slope of the load characteristic curve, mainly solving the parameter optimization problem at the macro level; the second correction factor accurately adjusts the cutting speed to adapt to the local characteristics of the coating through the deviation between the current surface coating roughness and the reference roughness, solving the adjustment needs at the micro level.

[0105] There is a close linkage effect between the two, forming an optimization mechanism of "trend and local" complementing each other. The first correction factor provides a global parameter framework, while the second correction factor is refined and supplemented within this framework. Through this linkage, the adjustment deviation caused by a single correction factor can be avoided. For example, relying solely on the first correction factor may ignore the microscopic characteristics of the coating surface, resulting in a decrease in local processing quality; relying solely on the second correction factor may lack the guidance of the global trend and fail to systematically optimize the load changes.

[0106] This linkage mechanism demonstrates a synergistic effect. The first correction factor analyzes the load characteristic trend to ensure that the processing parameters conform to the law of global load changes, providing directional guidance for overall optimization; the second correction factor further refines the processing parameters based on the microscopic characteristics of the coating surface. The combination of the two achieves mutual complementation and enhancement between macro trends and local characteristics, and can more comprehensively adapt to the processing needs of the target workpiece. Compared with the optimization of a single correction factor, this linkage mechanism can significantly improve the tool load adaptability and workpiece processing accuracy, and show better performance in complex processing scenarios.

[0107] The present invention adjusts the cutting speed in this way to optimize the tool load adaptability and processing stability. However, in actual application, other objective factors need to be considered comprehensively, such as processing efficiency, tool life, workpiece surface quality, and production rhythm. These factors are closely related to the adjustment of the cutting speed, and their dynamic changes may affect the overall performance of the processing process. Therefore, in the process of implementing the present invention, the relevant factors should be comprehensively evaluated and optimized according to the specific processing scenarios and needs to ensure that the final processing results meet the quality requirements and achieve a balance between efficiency and cost.

[0108] The following is a specific example to illustrate how to use the two correction factors, the average slope of the load characteristic curve and the surface coating roughness deviation, to comprehensively adjust the initial cutting speed to optimize the tool load and processing performance:

[0109] Assume that the initial cutting speed of the target workpiece is 1200RPM. By analyzing the historical processing logs, the first correction factor (average slope of the load characteristic curve) is 1.05, indicating that the load has a slight deterioration trend with the increase of coating thickness. At the same time, the current coating roughness value of the target workpiece is measured by visual inspection technology to be 0.52μm. Compared with the standard reference value of 0.50μm, the roughness deviation is calculated to be 4%, that is, the second correction factor is 0.04. In order to reasonably balance the influence of the two correction factors, the adjustment coefficient of the first correction factor is set to 0.3, and the adjustment coefficient of the second correction factor is set to 0.2.

[0110] First, multiply the first correction factor 1.05 by its adjustment coefficient 0.3 to obtain the adjustment contribution value of the correction factor of 0.315. Then, multiply the second correction factor 0.04 by its adjustment coefficient 0.2 to obtain the adjustment contribution value of the correction factor of 0.008. Then, add the two adjustment contribution values ​​and add them to the reference value 1 to form the final adjustment factor, which is 1.323. Finally, divide the initial cutting speed 1200RPM by the adjustment factor 1.323, and calculate the optimized cutting speed to be approximately 1130RPM.

[0111] Through this optimization adjustment, the cutting speed is slightly reduced from 1200RPM to 1130RPM, which reduces the tool load while maintaining the processing efficiency as much as possible, thus ensuring the improvement of the workpiece surface quality. The adjustment range is moderate, which can strike a balance between efficiency and tool life.

[0112] Furthermore, Figure 6 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0113] Among them, in another preferred embodiment provided by the present invention, a smart factory application system based on a real-time database includes:

[0114] The data acquisition module 100 is used to obtain the initial cutting speed of the target tool for the target workpiece, and extract the historical processing log of the target tool in the smart factory. At the same time, it uses visual inspection technology to identify the type of surface coating of the target workpiece in real time and obtain the current surface coating roughness value.

[0115] In the embodiment of the present invention, in the smart factory to which the present invention is applied, cutting processing is an important application scenario, and efficient and precise processing of the target workpiece is achieved through intelligent processing procedures. The smart factory integrates real-time databases, online monitoring equipment and visual inspection technology, can dynamically respond to processing requirements and optimize processing parameters, and provides a highly intelligent solution for the processing of special workpieces.

[0116] The initial cutting speed usually comes from a preset cutting process parameter library. This parameter library is based on the recommended values ​​provided by the tool manufacturer, combined with the basic properties of the workpiece material (such as hardness, strength) and the cutting environment (such as coolant usage conditions). However, in the prior art, the setting of the initial cutting speed rarely fully considers the impact of special coatings on the surface of the target workpiece. Special coatings may cause increased cutting forces, increased tool wear, and other phenomena, and this complexity is often ignored in traditional processes. Therefore, using only preset parameters may not be able to effectively meet the processing needs of target workpieces with special coatings.

[0117] The historical processing logs of the target tool are automatically recorded and stored in the real-time database of the smart factory. These logs include the cutting records of the target tool under different workpieces and different process parameters, such as cutting speed, cutting depth, coating thickness, spindle power, tool wear status and other key data. These data usually come from online monitoring equipment during the operation of the tool, such as spindle power sensors, cutting force sensors, and workpiece surface detection systems. Through the integrated analysis of these data, a performance model of the tool under specific processing conditions can be generated, providing a reference for the subsequent processing optimization of similar workpieces.

[0118] Real-time identification of the type of surface coating and the current coating roughness value of the target workpiece through visual inspection technology requires the help of high-precision industrial cameras and data processing algorithms. The industrial camera captures the surface of the target workpiece and collects image data; combined with multispectral imaging technology, the reflectivity and absorptivity characteristics of different coating materials within the spectral range are used to identify the type of coating. At the same time, the detection of coating roughness can be achieved through laser interferometry technology or optical profilometers. These devices can measure the microscopic characteristics of the surface with high precision and convert the results into roughness values. The detection process is linked to the real-time database to store the collected coating types and roughness data in real time, which is convenient for the adjustment of subsequent processing parameters. Through this intelligent detection process, it is possible to dynamically adapt to changes in the coating characteristics of the target workpiece and improve the accuracy and efficiency of processing.

[0119] Furthermore, the smart factory application system based on real-time database also includes:

[0120] The load characteristic curve drawing module 200 is used to parse the historical processing log, screen out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extract the load data of the target tool under different coating thickness conditions from the screened historical workpiece processing records, and generate a load characteristic curve in order of coating thickness from small to large.

[0121] Specifically, Figure 7 It shows a structural block diagram of the load characteristic curve drawing module 200 in the system provided by the embodiment of the present invention.

[0122] In a preferred embodiment of the present invention, the load characteristic curve drawing module 200 specifically includes:

[0123] The log screening unit 201 is used to parse the historical processing logs of the smart factory and screen out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type;

[0124] A matching data table collating unit 202 is used to extract the load data of the target tool under different coating thicknesses from the screened historical workpiece processing records, wherein the load data is the ratio of the spindle power to the rated power of the machine where the target tool is located, and to collate the data into a matching data table corresponding to the coating thickness and the load data;

[0125] The load characteristic curve generating unit 203 is used to generate a load characteristic curve based on the matching data table, with the coating thickness as the horizontal axis and the load data as the vertical axis.

[0126] In an embodiment of the present invention, the load data of the target tool under different coating thicknesses is extracted from the screened historical workpiece processing records, and the real-time database and online monitoring technology of the smart factory are relied on for implementation. First, the spindle power data and rated power value during the processing are extracted from the screened records through the historical processing log parsing technology, and the spindle power and rated power are calculated as the ratio of the spindle power to the rated power. This ratio can be completed by the automatic calculation module of the database and stored in the corresponding load data field. At the same time, the corresponding coating thickness information in each record is matched, and a matching table of coating thickness and load data is generated to ensure that the data is clear and complete.

[0127] The ratio of the spindle power to the rated power of the machine where the target tool is located is selected as the measurement indicator of load data, mainly because this ratio can intuitively reflect the changing characteristics of the tool cutting load. The spindle power is directly affected by the cutting force, and the rated power provides a benchmark value for mechanical performance. The actual load level of the machine can be quantified through the ratio of the two. At the same time, this ratio is dimensionless, which is convenient for data comparison and analysis under different working conditions. Although other types of load data can be selected, such as three-axis cutting force, vibration amplitude, etc., the acquisition of these data usually requires additional high-precision sensors, which is more complicated, while the spindle power ratio can be directly collected and calculated through existing equipment, which has higher practicality and consistency.

[0128] Furthermore, the smart factory application system based on real-time database also includes:

[0129] The first correction factor determination module 300 is used to analyze the load characteristic curve to determine whether it shows a positive trend. If so, it is determined that the surface coating type has a degradation characteristic on the load of the target tool, and the average slope value of the load characteristic curve is extracted as the first correction factor.

[0130] Specifically, Figure 8 It shows a structural block diagram of the first correction factor determination module 300 in the system provided by an embodiment of the present invention.

[0131] In a preferred embodiment of the present invention, the first correction factor determination module 300 specifically includes:

[0132] The trend analysis unit 301 is used to analyze the overall trend of the load characteristic curve to determine whether the load data presents an overall upward relationship with the increase of the coating thickness;

[0133] A degradation characteristic determination unit 302 is used to determine that the surface coating type has a degradation characteristic for the load of the target tool when it is determined that the load data as a whole increases with the coating thickness;

[0134] The average slope value calculation unit 303 is used to extract the average slope value based on the load characteristic curve and use it as the first correction factor.

[0135] In an embodiment of the present invention, the overall trend of the load characteristic curve is analyzed, and it is necessary to combine data fitting technology and statistical analysis methods for specific implementation. First, the load characteristic curve is trend analyzed by linear regression or polynomial fitting technology, and the overall relationship between the load data and the coating thickness is expressed by a mathematical model. Linear regression can provide a clear trend direction, while polynomial fitting is suitable for more complex nonlinear changes. By calculating the slope of the trend line, it can be determined whether the load data shows an overall upward relationship with the increase in coating thickness. If the slope is positive and the fitting result shows that the overall trend increases significantly, it is determined that the load has a positive relationship. This analysis applies existing statistical methods and curve fitting algorithms, and is usually completed by data analysis software or the factory's real-time database analysis module.

[0136] "Determining that the type of surface coating has degradation characteristics for the target tool load" is of great significance. Through this judgment, the degree and direction of the impact of the target workpiece surface coating on the tool load can be clarified. If it is determined to be a degradation characteristic, it means that the coating may increase the tool load, aggravate tool wear, and reduce processing efficiency. This conclusion not only provides a basis for the optimization of processing parameters, but also helps factories evaluate the processing feasibility of workpieces with different coatings, and even provides feedback for tool design and processing technology improvements. After clarifying the degradation characteristics, targeted adjustments can be made before processing to avoid tool failure or processing failure due to improper parameter settings.

[0137] The significance of adjusting the initial cutting speed by extracting the average slope value based on the load characteristic curve and using it as the first correction factor is to achieve dynamic optimization of processing parameters. The average slope value reflects the overall growth rate of the load as the coating thickness increases, and is the core indicator for quantifying the degree of load degradation. By introducing this correction factor, the cutting speed can be optimized in a targeted manner based on historical data and coating characteristics to ensure that the processing parameters match the characteristics of the target workpiece. The advantage of such an adjustment is that it can reduce the instantaneous load peak of the tool, extend the tool life, and improve processing stability and surface quality. Compared with the traditional static parameter setting method, this dynamic adjustment is based on actual data trends, can better adapt to changes in complex workpieces and processing conditions, and improve the processing efficiency and precision of smart factories.

[0138] Furthermore, the smart factory application system based on real-time database also includes:

[0139] The second correction factor determination module 400 is used to analyze the load characteristic curve, identify load anomaly points, locate the surface coating roughness values ​​of historical workpieces corresponding to these load anomaly points through historical processing logs, and perform statistical analysis on these surface coating roughness values ​​to generate standardized reference surface coating roughness values, and calculate the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor.

[0140] Specifically, Fig. 9 It shows a structural block diagram of the second correction factor determination module 400 in the system provided by an embodiment of the present invention.

[0141] In a preferred embodiment of the present invention, the second correction factor determination module 400 specifically includes:

[0142] The load abnormal point determination unit 401 is used to analyze the load characteristic curve and screen out the load abnormal point, wherein the load abnormal point refers to a point where the load data does not increase with the increase of coating thickness according to the overall trend of the load characteristic curve, but the load data decreases or remains unchanged;

[0143] The reference roughness value generating unit 402 is used to locate the historical workpiece processing records corresponding to these load abnormal points through the historical processing logs of the smart factory, extract the surface coating roughness values ​​of these historical workpieces, and perform statistical analysis on them, and use the method of calculating the average value or selecting the median value after denoising to generate a standardized reference surface coating roughness value;

[0144] The deviation quantification unit 403 is used to compare the current surface coating roughness value of the target workpiece with the reference surface coating roughness value, quantify the deviation between the two, and use it as the second correction factor.

[0145] In the embodiment of the present invention, the significance of screening outlier load points is to identify outlier data that does not conform to the overall trend by analyzing the load characteristic curve, thereby revealing the potential impact of coating characteristics on tool load. Outliers are usually manifested as load data that decreases, remains unchanged, or increases significantly below the normal trend as the coating thickness increases. These outliers may be closely related to the local characteristics of the coating on the workpiece surface, especially when the coating roughness is too low, uneven, or there are local anomalies. By screening these data points, the specific impact of surface coating roughness on load changes can be further analyzed, and key factors that have a significant impact on tool performance and processing stability can be found, thereby providing a more targeted reference for processing parameter optimization.

[0146] Through the historical processing logs of the smart factory, the historical workpiece processing records corresponding to the load abnormal points are located, which requires real-time database and data analysis technology. The specific implementation process includes the following steps: First, extract the abnormal point data marked in the load characteristic curve and obtain the workpiece identification code associated with these points; then, through the historical processing log query interface of the smart factory, locate the coating thickness, cutting parameters and coating roughness values ​​of these workpieces during the processing process; then, perform statistical analysis on the extracted surface coating roughness values, and use the denoising technology in signal processing (such as filtering or threshold removal) to remove abnormal data points to ensure the reliability and representativeness of the data; finally, calculate the average value of the roughness value or select the median value to generate a standardized reference surface coating roughness value. In this process, existing technologies such as database query, statistical analysis and signal processing are used to ensure that the generated reference value can truly reflect the coating characteristics of the load abnormal points.

[0147] Furthermore, the smart factory application system based on real-time database also includes:

[0148] The cutting speed optimization module 500 is used to combine the first correction factor and the second correction factor to perform comprehensive correction on the initial cutting speed and calculate the optimized cutting speed.

[0149] In the embodiment of the present invention, the significance of the linkage between the first correction factor and the second correction factor is to combine the load characteristic trend with the local characteristics of the coating surface to build a more comprehensive processing parameter optimization model. The first correction factor quantifies the overall trend of the load changing with the coating thickness based on the average slope of the load characteristic curve, mainly solving the parameter optimization problem at the macro level; the second correction factor accurately adjusts the cutting speed to adapt to the local characteristics of the coating through the deviation between the current surface coating roughness and the reference roughness, solving the adjustment needs at the micro level.

[0150] There is a close linkage effect between the two, forming an optimization mechanism of "trend and local" complementing each other. The first correction factor provides a global parameter framework, while the second correction factor is refined and supplemented within this framework. Through this linkage, the adjustment deviation caused by a single correction factor can be avoided. For example, relying solely on the first correction factor may ignore the microscopic characteristics of the coating surface, resulting in a decrease in local processing quality; relying solely on the second correction factor may lack the guidance of the global trend and fail to systematically optimize the load changes.

[0151] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0152] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0153] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A smart factory application method based on real-time database, characterized in that: The method comprises: Obtain the initial cutting speed of the target tool for the target workpiece, extract the historical processing log of the target tool in the smart factory, and use visual inspection technology to identify the type of surface coating of the target workpiece in real time and obtain the current surface coating roughness value; Analyze the historical processing logs, select the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extract the load data of the target tool under different coating thickness conditions from the selected historical workpiece processing records, and generate a load characteristic curve in order of coating thickness from small to large; Analyze the load characteristic curve to determine whether it shows a positive trend. If so, determine that the type of surface coating has a deterioration characteristic on the load of the target tool, and extract the average slope value of the load characteristic curve as the first correction factor; Analyze the load characteristic curve, identify the load abnormal points, locate the surface coating roughness values ​​of the historical workpieces corresponding to these load abnormal points through the historical processing logs, perform statistical analysis on these surface coating roughness values, generate standardized reference surface coating roughness values, and calculate the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor; The initial cutting speed is comprehensively corrected by combining the first correction factor and the second correction factor, and the optimized cutting speed is calculated.

2. The intelligent factory application method based on real-time database according to claim 1 is characterized in that: The steps of parsing the historical processing log, screening out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extracting the load data of the target tool under different coating thickness conditions from the screened historical workpiece processing records, and generating a load characteristic curve in order of coating thickness from small to large include: Analyze the historical processing logs of the smart factory and select the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type; Extract the load data of the target tool under different coating thicknesses from the selected historical workpiece processing records, where the load data is the ratio of the spindle power to the rated power of the machine where the target tool is located, and organize it into a matching data table corresponding to the coating thickness and load data; Based on the matching data table, a load characteristic curve is generated with coating thickness as the horizontal axis and load data as the vertical axis.

3. The intelligent factory application method based on real-time database according to claim 1 is characterized in that: The steps of analyzing the load characteristic curve to determine whether it shows a positive trend, and if so, determining that the type of surface coating has a degradation characteristic on the load of the target tool, and extracting the average slope value of the load characteristic curve as the first correction factor include: Analyze the overall trend of the load characteristic curve to determine whether the load data shows an overall upward relationship with the increase of coating thickness; If it is determined that the load data as a whole increases with the coating thickness, it is determined that the type of surface coating has a deteriorating characteristic for the load of the target tool; Based on the load characteristic curve, an average slope value is extracted and used as the first correction factor.

4. The intelligent factory application method based on real-time database according to claim 1 is characterized in that: The steps of analyzing the load characteristic curve, identifying the load abnormal points, locating the surface coating roughness values ​​of the historical workpieces corresponding to these load abnormal points through the historical processing logs, and performing statistical analysis on these surface coating roughness values ​​to generate standardized reference surface coating roughness values, and calculating the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor include: Analyze the load characteristic curve and screen out abnormal load points, where the load data does not increase as the coating thickness increases according to the overall trend of the load characteristic curve, but decreases or remains unchanged; Through the historical processing logs of the smart factory, the historical workpiece processing records corresponding to these load anomalies are located, the surface coating roughness values ​​of these historical workpieces are extracted, and statistical analysis is performed on them. The average value is calculated or the median value is selected after denoising to generate a standardized reference surface coating roughness value; The current surface coating roughness value of the target workpiece is compared with the reference surface coating roughness value, and the deviation between the two is quantified and used as the second correction factor.

5. The intelligent factory application method based on real-time database according to claim 1 is characterized in that: Combining the first correction factor and the second correction factor, the initial cutting speed is comprehensively corrected, and the steps of calculating the optimized cutting speed include: The cutting speed optimization formula is retrieved, and the initial cutting speed is comprehensively corrected by combining the first correction factor and the second correction factor, and the optimized cutting speed is calculated; The optimized cutting speed is applied to the cutting process of the target tool.

6. The intelligent factory application method based on real-time database according to claim 5 is characterized in that: The cutting speed optimization formula is: , where N opt Refers to the optimized cutting speed, N init refers to the initial cutting speed, F1 refers to the first correction factor, that is, the average slope value of the load characteristic curve, K1 is the adjustment coefficient for adjusting the first correction factor, F2 is the second correction factor, that is, the deviation between the current surface coating roughness value and the reference surface coating roughness value, K2 is the adjustment coefficient for adjusting the second correction factor, and the value range of K1 and K2 is 0.1 to 0.5; In the cutting speed optimization formula, , where R current Refers to the current surface coating roughness value, R ref Refers to the reference surface coating roughness value.

7. A smart factory application system based on real-time database, characterized in that: The system comprises: a data acquisition module, a load characteristic curve drawing module, a first correction factor determination module, a second correction factor determination module and a cutting speed optimization module, wherein: The data acquisition module is used to obtain the initial cutting speed of the target tool for the target workpiece, and extract the historical processing log of the target tool in the smart factory. At the same time, it uses visual inspection technology to identify the type of surface coating of the target workpiece in real time and obtain the current surface coating roughness value; A load characteristic curve drawing module is used to parse historical processing logs, screen out historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type, extract the load data of the target tool under different coating thickness conditions from the screened historical workpiece processing records, and generate a load characteristic curve in order of coating thickness from small to large; A first correction factor determination module is used to analyze the load characteristic curve to determine whether it shows a positive trend. If so, it is determined that the type of surface coating has a degradation characteristic on the load of the target tool, and the average slope value of the load characteristic curve is extracted as the first correction factor; The second correction factor determination module is used to analyze the load characteristic curve, identify the load abnormal points, locate the surface coating roughness values ​​of the historical workpieces corresponding to these load abnormal points through the historical processing logs, and perform statistical analysis on these surface coating roughness values ​​to generate standardized reference surface coating roughness values, and calculate the deviation between the current surface coating roughness value of the target workpiece and the reference surface coating roughness value as the second correction factor; The cutting speed optimization module is used to combine the first correction factor and the second correction factor to comprehensively correct the initial cutting speed and calculate the optimized cutting speed.

8. The intelligent factory application system based on real-time database according to claim 7 is characterized in that: The load characteristic curve drawing module specifically includes: The log screening unit is used to parse the historical processing logs of the smart factory and screen out the historical workpiece processing records that are consistent with the target workpiece type and have the same surface coating type; A matching data table arrangement unit is used to extract the load data of the target tool under different coating thicknesses from the screened historical workpiece processing records, wherein the load data is the ratio of the spindle power to the rated power of the machine where the target tool is located, and arrange it into a matching data table corresponding to the coating thickness and the load data; The load characteristic curve generating unit is used to generate a load characteristic curve based on the matching data table, with the coating thickness as the horizontal axis and the load data as the vertical axis.

9. The intelligent factory application system based on real-time database according to claim 8 is characterized in that: The first correction factor determination module specifically includes: The trend analysis unit is used to analyze the overall trend of the load characteristic curve to determine whether the load data shows an overall upward relationship with the increase of coating thickness; A degradation characteristic determination unit, for determining that the surface coating type has a degradation characteristic for the load of the target tool when it is determined that the load data as a whole increases with the coating thickness; The average slope value calculation unit is used to extract the average slope value based on the load characteristic curve and use it as the first correction factor.

10. The intelligent factory application system based on real-time database according to claim 9 is characterized in that: The second correction factor determination module specifically includes: A load abnormal point determination unit is used to analyze the load characteristic curve and screen out load abnormal points, wherein the load abnormal point refers to a point where the load data does not increase as the coating thickness increases according to the overall trend of the load characteristic curve, but decreases or remains unchanged; A reference roughness value generating unit is used to locate the historical workpiece processing records corresponding to these load abnormal points through the historical processing logs of the smart factory, extract the surface coating roughness values ​​of these historical workpieces, and perform statistical analysis on them, and generate a standardized reference surface coating roughness value by calculating the average value or selecting the median value after denoising; The deviation quantification unit is used to compare the current surface coating roughness value of the target workpiece with the reference surface coating roughness value, quantify the deviation between the two, and use it as the second correction factor.

Images